Outline Generator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill accepts untrusted user input (topics and summaries) which it uses to influence its reasoning and output. This constitutes an indirect prompt injection surface. * Ingestion points: Topic/summary input from user (SKILL.md workflow step 1). * Boundary markers: Absent; the user input is not delimited from instructions. * Capability inventory: None. The skill does not use tools, execute commands, or access files. * Sanitization: None; input is processed directly as natural language.
- [No Code] (INFO): The skill consists entirely of natural language instructions and does not contain any executable scripts or configuration files.
Audit Metadata